Prediction of geogenic source of groundwater fluoride contamination in Indian states: A comparative study of different supervised machine learning algorithms

India has been dealing with fluoride contamination of groundwater for the past few decades. Long-term exposure of fluoride can cause skeletal and dental fluorosis. Therefore, an in-depth exploration of fluoride concentrations in different parts of India is desirable. This work employs machine learning algorithms to analyze the fluoride concentrations in five major affected Indian states (Andhra Pradesh, Rajasthan, Tamil Nadu, Telangana and West Bengal). A correlation matrix was used to identify appropriate predictor variables for fluoride prediction. The various algorithms used for predictions included K-nearest neighbor (KNN), logistic regression (LR), random forest (RF), support vector classifier (SVC), Gaussian NB, MLP classifier, decision tree classifier, gradient boosting classifier, voting classifier soft and voting classifier hard. The performance of these models is assessed over accuracy, precision, recall and error rate and receiver operating curve. As the dataset was skewed, the performance of models was evaluated before and after resampling. Analysis of results indicates that the RF model is the best model for predicting fluoride contamination in groundwater in Indian states.

Fluoride in groundwater of industrial town of Sonbhadra district, Uttar Pradesh, India: probable release mechanism and potential health risk assessment

In the selected study region of Sonbhadra district, coal burning and mining activities are dominant. Previous studies reported F contamination in very few groundwater samples of this region. A detailed study is required to estimate the fluoride in groundwater of this area. Hence, a total of 128 groundwater samples were collected during post- and pre-monsoon seasons in the year 2017 to estimate the F-, its geochemistry, and health risk assessment from Renukoot and Anpara industrial clusters of Sonbhadra district, Uttar Pradesh, India. The pH of groundwater samples varied from slightly acidic to alkaline during both seasons. Almost all the major cations (Ca2+, Mg2+, Na+, and K+) and major anions (HCO3-, Cl-, SO42-, and F-) values in groundwater samples of both clusters were found within the permissible limit of World Health Organization (WHO) and Beauro of Indian standards except F- in both seasons. The scatter plots of F- with Ca2+, Na+, HCO3-, and pH are used to explain the release mechanism of fluoride in groundwater. Saturation indices (SI) calcite versus SI fluorite and SI dolomite versus SI fluorite plots of both clusters used to check the involvement of these minerals in fluoride enrichment of aquifers. F- contamination in groundwater due to coal burning in coal mining and thermal power plant dominated region is discussed globally and locally both. The non-carcinogenic health risk due to consumption of fluoride-contaminated water is estimated by using target hazard quotient (THQ). THQ values of F- showed that children are at high risk than adults in both clusters of the study area during both seasons. Pictorial representation is used to show the dental fluorosis cases in children of the study region.

Groundwater fluoride contamination, probable release, and containment mechanisms: a review on Indian context

Fluoride contamination in the groundwater has got great attention in last few decades due to their toxicity, persistent capacity and accumulation in human bodies. There are several sources of fluoride in the environment and different pathways to enter in the drinking water resources, which is responsible for potential effect on human health. Presence of high concentration of fluoride ion in groundwater is a major issue and it makes the water unsuitable for drinking purpose. Availability of fluoride in groundwater indicates various geochemical processes and subsurface contamination of a particular area. Fluoride-bearing aquifers, geological factors, rate of weathering, ion-exchange reaction, residence time and leaching of subsurface contaminants are major responsible factors for availability of fluoride in groundwater. In India, several studies have reported that the groundwater of several states are contaminated with high fluoride. The undesirable level of fluoride in groundwater is one of the most natural groundwater quality problem, which affects large portion of arid and semiarid regions of India. Rajasthan, Andhra Pradesh, Telangana, Tamil Nadu, Gujarat, and West Bengal are the relatively high-fluoride-contaminated states in India. Chronic ingestion of high doses of fluoride-rich water leads to fluorosis on human and animal. Over 66 million Indian populations are at risk due to excess fluoride-contaminated water. Therefore, groundwater contamination subject to undesirable level of fluoride needs urgent attention to understand the role of geochemistry, hydrogeology and climatic factors along with anthropogenic inputs in fluoride pollution.

Assessment of Yamuna and associated drains used for irrigation in rural and peri-urban settings of Delhi NCR

The present study assessed the quality of Yamuna River and the Najafgarh drain water for irrigational purposes in the Delhi region in terms of spatial variations in the physicochemical characteristics as well as heavy metal concentrations. The monitoring was done for the period July 2012-August 2013 representing pre-monsoon, monsoon, and post-monsoon sessions and considering six physicochemical parameters. Heavy metals such as cadmium, chromium, copper, nickel, zinc, and lead have been found in the river due to rampant discharge of industrial effluents into the river. The mean metal concentrations in the 15 sampling sites were in the range of (mg L(-1)) 0.02-0.64 (Cu), 0-0.42 (Cr), 0.13-2.22(Zn), 0.03-0.27 (Pb), 0-0.07 (Cd), and 0.01-0.13 (Ni). Multivariate statistics (PCA and HCA) were used to identify the possible sources of metal contamination and to examine the spatial changes in the Yamuna River as well as in the Najafgarh drain. This study reveals the occurrence of mean Cd concentration above the safe limit at Palla, Christian Ashram and Jagatpur of the Yamuna river while Punjabi Bagh of the Najafgarh drain necessitate treatment in terms of heavy metals such as Cd, Cu, Cr, Ni, Pb, and Zn before it could be rendered useful for irrigation.